基于EEMD能量熵与ANN的矿用异步电机故障诊断

针对矿用异步电机故障时定子电流信号非线性非平稳性的特点，提出了一种基于集合经验模态分解（EEMD）能量熵与人工神经网络（ANN）结合的转子故障诊断方法。首先利用EEMD将电机定子电流信号分解为一系列本征模态函数（IMF）；其次通过互相关准则，选取信息最丰富的IMF分量并计算其能量熵来构造故障特征向量；最后将特征向量输入人工神经网络（ANN）进行训练和状态识别。实验通过Ansys Maxwell软件对故障电机建模获得仿真电流数据，验证了该方法是一种可行的矿用电机故障诊断方法，相较于传统频谱分析更为可靠，可实现对异步电机处于正常、转子断条、气隙偏心等状态的准确识别，综合识别率达97%。

Fault Diagnosis of Mine Asynchronous Motor Based on EEMD Energy Entropy and ANN

Aiming at the non-linear and non-stationary characteristics of stator current signal of mine asynchronous motor in case of fault, This paper proposes a rotor fault diagnosis method based on the combination of Ensemble Empirical Mode Decomposition (EEMD) energy entropy and Artificial Neural Network (ANN). Firstly, EEMD is used to decompose the stator current signal into a series of Intrinsic Mode Function (IMF); Secondly, the IMF component with the most abundant information is selected by cross-correlation criterion and its energy entropy is calculated to construct Fault eigenvector; Finally, the Fault eigenvector is input into the Artificial Neural Network (ANN) for training and state recognition. In the experiment, the faulty motor is modeled by ANSYS Maxwell software to obtain the simulation current data, It is verified that this method is feasible for fault diagnosis of mine motors, Compared with the traditional spectrum analysis, this method is more reliable and can accurately identify different status of motors, including normal state, rotor broken bars, and air gap eccentricity, The comprehensive recognition rate was 97%.